AI Paper Atlas

Research map / Vision-language and multimodal / Robot action and navigation

Dita: Scaling Diffusion Transformer for Generalist Vision-Language-Action Policy

Zhi Hou, Tianyi Zhang, Yuwen Xiong, Haonan Duan, Hengjun Pu, Ronglei Tong, Chengyang Zhao, Xizhou Zhu, Yu Qiao, Jifeng Dai, Yuntao Chen

ICCV 2025 · Vision-language and multimodal › Robot action and navigation · approach: Vision-language-action foundation models · 67 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
replace diffusion action head with in-context conditioning in the DiT (ablation)Dita · CALVIN ABC->Daverage length: 3.16 -> 3.61Improved
add OXE pretraining (ablation)Dita · CALVIN ABC->Daverage length: 2.38 -> 3.61Improved
increase observation frames from 2 to 3 (ablation)Dita · ManiSkill2avg success rate (%): 65.8% -> 35.4%Hurt
use 2 observation frames instead of 1 (ablation)Dita · ManiSkill2avg success rate (%): 61.6% -> 65.8%Improved
increase trajectory length from 2 to 32 (ablation)Dita · ManiSkill2avg success rate (%): 40.8% -> 65.8%Improved
in-context conditioning instead of AdaLN DiT (ablation)Dita · CALVIN ABC->D (no pretraining)average length: 1.45 -> 2.56Improved
add learning rate decay in finetuning (ablation)Dita · CALVIN ABC->Daverage length: 3.43 -> 3.61Improved
scale transformer from 12 to 24 layers (ablation)Dita without pretraining · CALVIN ABC->Daverage length: 2.56 -> 2.61Improved
add image augmentation during finetuning (ablation)Dita · CALVIN ABC->Daverage length: 3.61 -> 3.78Improved
reduce DDIM inference steps from 20 to 2 (ablation)Dita · SimplerEnv Pick Coke (variant)success rate (%): 85.5 -> 70.4Hurt
reduce DDIM inference steps from 20 to 10 (ablation)Dita · SimplerEnv Pick Coke (variant)success rate (%): 85.5 -> 85.3No clear effect
larger shuffle buffer (256000 vs 128000) (ablation)Dita · SimplerEnv coke_can (match)success rate (%): 71.2% -> 83.7%Improved

Later papers that compared with this method

2 later accepted papers report Dita as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy